Dart Query
The MCP server for Dart AI task management, focusing on batch operations and minimal context usage. It efficiently updates a large number of tasks through DartQL selectors and server-side batch processing.
rating : 2 points
downloads : 0
What is Dart-Query?
Dart-Query is an MCP server specifically designed for the Dart AI task management platform. It solves the problem of consuming a large number of context tokens when processing tasks one by one in the traditional way through an innovative batch operation method. With Dart-Query, you can update, delete, or query a large number of tasks at once without filling up the context window.How to use Dart-Query?
Using Dart-Query requires three basic steps: first, obtain your Dart AI API token; then, configure the server in the MCP client; finally, use various tools for task management. The server supports both single-task operation and batch operation modes.Applicable scenarios
Dart-Query is particularly suitable for scenarios that require batch management of tasks, such as batch updating task status, batch assigning tasks to team members, batch adding tags, batch setting due dates, batch importing task data, etc. It is especially useful for project managers and team leaders who manage a large number of tasks.Main features
Batch operations
Supports batch updating and deleting tasks. Use DartQL selectors to precisely locate the task groups to be operated on, avoiding processing tasks one by one.
DartQL selectors
Similar to SQL query syntax, it can precisely filter the tasks to be operated on, such as: dartboard = 'Engineering' AND priority = 'high'.
CSV batch import
Supports batch importing tasks from a CSV file. It includes a verification stage to ensure data quality and prevent incorrect data from entering the system.
Preview mode
All batch operations support the preview mode. You can first view the number and content of the tasks affected by the operation, and then execute it after confirmation.
Task CRUD
Complete single-task operation functions, including creating, reading, updating, and deleting tasks, as well as adding task comments.
Document management
Supports creating, reading, updating, and deleting documents, facilitating the management of project-related documents and instructions.
Advantages
Significantly reduce token consumption: The batch update of 50 tasks is reduced from about 30K tokens to about 200 tokens.
Zero context pollution: Batch operations do not generate a large amount of JSON data to pollute the context in the intermediate steps.
Efficient batch processing: Process hundreds of tasks at once, improving work efficiency.
Safe operation: Supports the preview mode and confirmation mechanism to avoid misoperations.
Flexible query ability: DartQL provides powerful task filtering functions.
Limitations
Only supports the Dart AI platform: Cannot be used for other task management tools.
Requires an API token: You need to obtain an access token from your Dart AI account.
Production environment operation: All operations directly affect production data and need to be used with caution.
Learning curve: You need to understand the DartQL syntax to fully utilize the batch functions.
How to use
Obtain an API token
Visit the Dart AI website (https://app.dartai.com/?settings=account), log in to your account, and copy the API token (starting with dsa_) in the account settings.
Configure the MCP client
Add the Dart-Query server configuration according to the MCP client you are using. It is recommended to install it using the npx method.
Verify the connection
Use the info tool to verify whether the server connection is normal and view the workspace configuration and available functions.
Start using
Use the corresponding tools according to your needs: single-task operation, batch operation, query, or document management.
Usage examples
Batch update high-priority tasks of the engineering team
Update the status of all high-priority tasks on the engineering dashboard to 'Doing'.
Batch add tags and set due dates
Add the 'urgent' tag to all tasks that contain the 'bug' tag and have a due date after today.
Batch archive completed tasks
Batch delete (move to the recycle bin) tasks that have a status of 'Done' and a completion time more than 30 days ago.
Batch create tasks from a CSV file
Batch create new tasks from a project plan CSV file.
Frequently Asked Questions
What is the difference between Dart-Query and directly using the Dart AI API?
Can the tasks deleted in batch be restored?
What query conditions does DartQL support?
How to ensure the safety of batch operations?
How much can the token consumption be reduced?
What types of task updates are supported?
Related resources
Dart AI official website
The official website of the Dart AI task management platform
Complete tool documentation
Detailed tool parameter reference, DartQL syntax, and CSV import format
GitHub repository
The source code of the Dart-Query MCP server
MCP protocol documentation
The official documentation of the Model Context Protocol
API token acquisition
The page to obtain the Dart AI API token

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.2K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.7K
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.3K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.1K
5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
47.4K
4.8 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.0K
4.5 points



